The competitive society in the new era calls for more research to improve the well-being of workers as well as to improve their productivity. Knowledge workers face a high mental workload in terms of planning and coordination. One solution is to predict the mental workload of knowledge workers. Some machine learning models have been implemented for mental workload prediction, but deep learning models are yet to be introduced for this purpose. Deep learning models are superior to machine learning models because of their ability to correct inaccurate predictions if they ever occur. Therefore, this study aims to optimize the extreme learning adaptive neuro-fuzzy inference system (ELANFIS) by integrating particle swarm optimization into a micro-genetic algorithm to predict the mental workload of knowledge workers. Although the adaptive neuro-fuzzy inference system (ANFIS) shows reasonable prediction performance, it also suffers from the curse of dimensionality and has a poor computation time. Thus, ELANFIS is introduced because its curse of dimensionality is less severe when solving problems with a high number of input dimensions. The integration of the advantages of a micro-genetic algorithm and particle swarm optimization is suggested to optimize the premise parameters of ELANFIS, as this can allow better solutions to be located at a faster rate. The proposed model yields promising prediction results, with improvements of 6.0665 in the Mean Squared Error(MSE) and 1.279 in the Root Mean Squared Error (RMSE) for regression; the proposed model even surpasses the prediction results of ELANFIS optimized with PSO alone, with improvements of 1.5369 in MSE and 0.4094 in RMSE for regression. The findings are expected to assist employers in determining an appropriate working lifestyle for their employees.

新时代的竞争社会要求进行更多的研究，以改善工人的福利并提高其生产率。知识工作者在计划和协调方面面临着很高的心理工作量。一种解决方案是预测知识型员工的心理工作量。一些机器学习模型已经用于心理工作负荷预测，但是为此目的还没有引入深度学习模型。深度学习模型优于机器学习模型，因为它们能够纠正不准确的预测（如果曾经发生过）。因此，本研究旨在通过将粒子群优化算法集成到微遗传算法中来预测知识型员工的心理工作量，从而优化极限学习自适应神经模糊推理系统（ELANFIS）。尽管自适应神经模糊推理系统（ANFIS）表现出合理的预测性能，但它也遭受了维数的诅咒，并且计算时间很短。因此，引入ELANFIS是因为它在解决输入维数众多的问题时对维数的诅咒不太严重。建议将微遗传算法的优势与粒子群优化技术相结合，以优化ELANFIS的前提参数，因为这样可以更快地找到更好的解决方案。所提出的模型产生了有希望的预测结果，均方根误差（MSE）改善了6.0665，而均方根误差（RMSE）改善了1.279，可以进行回归；该模型甚至超过了单独使用PSO优化的ELANFIS的预测结果，MSE的改进为1.5369，0的改进。RMSE中的4094用于回归。研究结果有望帮助雇主确定适合其雇员的工作生活方式。